Editing Authentication (section)

==== Continuous authentication ====
Conventional computer systems authenticate users only at the initial log-in session, which can be the cause of a critical security flaw. To resolve this problem, systems need continuous user authentication methods that continuously monitor and authenticate users based on some biometric trait(s). A study used behavioural biometrics based on writing styles as a continuous authentication method.<ref name="BROC2017">Brocardo ML, Traore I, Woungang I, Obaidat MS. "[http://onlinelibrary.wiley.com/doi/10.1002/dac.3259/full Authorship verification using deep belief network systems] {{webarchive|url=https://web.archive.org/web/20170322015517/http://onlinelibrary.wiley.com/doi/10.1002/dac.3259/full |date=2017-03-22 }}". Int J Commun Syst. 2017. {{doi|10.1002/dac.3259}}</ref><ref name="Patel 49–61">{{Cite journal|last1=Patel|first1=Vishal M.|last2=Chellappa|first2=Rama|last3=Chandra|first3=Deepak|last4=Barbello|first4=Brandon|date=July 2016|title=Continuous User Authentication on Mobile Devices: Recent progress and remaining challenges|journal=IEEE Signal Processing Magazine|volume=33|issue=4|pages=49–61|doi=10.1109/msp.2016.2555335|bibcode=2016ISPM...33...49P|s2cid=14179050|issn=1053-5888}}</ref>

Recent research has shown the possibility of using smartphones sensors and accessories to extract some behavioral attributes such as touch dynamics, [[keystroke dynamics]] and [[gait recognition]].<ref>{{Cite book|last1=De Marsico|first1=Maria|last2=Fartade|first2=Eduard Gabriel|last3=Mecca|first3=Alessio|chapter=Feature-based Analysis of Gait Signals for Biometric Recognition - Automatic Extraction and Selection of Features from Accelerometer Signals |date=2018|title=Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods|pages=630–637|publisher=SCITEPRESS - Science and Technology Publications|doi=10.5220/0006719106300637|isbn=978-989-758-276-9|doi-access=free}}</ref> These attributes are known as behavioral biometrics and could be used to verify or identify users implicitly and continuously on smartphones. The authentication systems that have been built based on these behavioral biometric traits are known as active or continuous authentication systems.<ref name="MAHFOUZ201728">{{Cite journal |doi = 10.1016/j.jisa.2017.10.002|title = A survey on behavioral biometric authentication on smartphones|journal = Journal of Information Security and Applications|volume = 37|pages = 28–37|year = 2017|last1 = Mahfouz|first1 = Ahmed|last2 = Mahmoud|first2 = Tarek M.|last3 = Eldin|first3 = Ahmed Sharaf|arxiv = 1801.09308|s2cid = 21265344}}</ref><ref name="Patel 49–61" />